INDEX

Explanations

assertions about similarity and uniqueness in experiences or objects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-0.94

ValueStyle

-0.76

parsedMessage

-0.57

 <=",

-0.56

//

-0.54

ագրություններ

-0.54

AttributedString

-0.54

paksa

-0.53

IsContent

-0.53

adpleegd

-0.53

POSITIVE LOGITS

 random

0.68

 unique

0.67

srand

0.66

 randomly

0.61

 RANDOM

0.59

 UNIQUE

0.59

 different

0.58

Chaque

0.58

 every

0.57

UNIQUE

0.57

Activations Density 0.452%

assertions about similarity and uniqueness in experiences or objects

No Comments

No Known Activations